Rendering automatic bokeh recommendation engine for photos using deep learning algorithm
Automatic bokeh is one of the smartphone’s essential photography effects. This effect enhances the quality of the image where the subject background gets out of focus by providing a soft (i.e., diverse) background. Most smartphones have a single rear camera that is lacking to provide which effects n...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Sciendo
2022-12-01
|
| Series: | Acta Universitatis Sapientiae: Informatica |
| Subjects: | |
| Online Access: | https://doi.org/10.2478/ausi-2022-0015 |
| _version_ | 1811159158853992448 |
|---|---|
| author | Kumar Rakesh Gupta Meenu Jaismeen Dhanta Shreya Pathak Nishant Kumar Vivek Yukti Sharma Ayush Deepak Ramola Gaurav Velusamy Sudha |
| author_facet | Kumar Rakesh Gupta Meenu Jaismeen Dhanta Shreya Pathak Nishant Kumar Vivek Yukti Sharma Ayush Deepak Ramola Gaurav Velusamy Sudha |
| author_sort | Kumar Rakesh |
| collection | DOAJ |
| description | Automatic bokeh is one of the smartphone’s essential photography effects. This effect enhances the quality of the image where the subject background gets out of focus by providing a soft (i.e., diverse) background. Most smartphones have a single rear camera that is lacking to provide which effects need to be applied to which kind of images. To do the same, smartphones depend on different software to generate the bokeh effect on images. Blur, Color-point, Zoom, Spin, Big Bokeh, Color Picker, Low-key, High-Key, and Silhouette are the popular bokeh effects. With this wide range of bokeh types available, it is difficult for the user to choose a suitable effect for their images. Deep Learning (DL) models (i.e., MobileNetV2, InceptionV3, and VGG16) are used in this work to recommend high-quality bokeh effects for images. Four thousand five hundred images are collected from online resources such as Google images, Unsplash, and Kaggle to examine the model performance. 85% accuracy has been achieved for recommending different bokeh effects using the proposed model MobileNetV2, which exceeds many of the existing models. |
| first_indexed | 2024-04-10T05:37:26Z |
| format | Article |
| id | doaj.art-1359ccf93c104dfcab4f521722e7a853 |
| institution | Directory Open Access Journal |
| issn | 2066-7760 |
| language | English |
| last_indexed | 2024-04-10T05:37:26Z |
| publishDate | 2022-12-01 |
| publisher | Sciendo |
| record_format | Article |
| series | Acta Universitatis Sapientiae: Informatica |
| spelling | doaj.art-1359ccf93c104dfcab4f521722e7a8532023-03-06T17:00:03ZengSciendoActa Universitatis Sapientiae: Informatica2066-77602022-12-0114224827210.2478/ausi-2022-0015Rendering automatic bokeh recommendation engine for photos using deep learning algorithmKumar Rakesh0Gupta Meenu1Jaismeen2Dhanta Shreya3Pathak Nishant Kumar4Vivek Yukti5Sharma Ayush6Deepak7Ramola Gaurav8Velusamy Sudha9Chandigarh University, Punjab, IndiaChandigarh University, Punjab, IndiaChandigarh University, Punjab, IndiaChandigarh University, Punjab, IndiaChandigarh University, Punjab, IndiaChandigarh University, Punjab, IndiaChandigarh University, Punjab, IndiaChandigarh University, Punjab, IndiaSamsung Research Institute, Banglore, IndiaSamsung Research Institute, Banglore, IndiaAutomatic bokeh is one of the smartphone’s essential photography effects. This effect enhances the quality of the image where the subject background gets out of focus by providing a soft (i.e., diverse) background. Most smartphones have a single rear camera that is lacking to provide which effects need to be applied to which kind of images. To do the same, smartphones depend on different software to generate the bokeh effect on images. Blur, Color-point, Zoom, Spin, Big Bokeh, Color Picker, Low-key, High-Key, and Silhouette are the popular bokeh effects. With this wide range of bokeh types available, it is difficult for the user to choose a suitable effect for their images. Deep Learning (DL) models (i.e., MobileNetV2, InceptionV3, and VGG16) are used in this work to recommend high-quality bokeh effects for images. Four thousand five hundred images are collected from online resources such as Google images, Unsplash, and Kaggle to examine the model performance. 85% accuracy has been achieved for recommending different bokeh effects using the proposed model MobileNetV2, which exceeds many of the existing models.https://doi.org/10.2478/ausi-2022-0015bokehrecommendationphotographydeep learninginceptionv3vgg16mobilenetv2effects68r15 |
| spellingShingle | Kumar Rakesh Gupta Meenu Jaismeen Dhanta Shreya Pathak Nishant Kumar Vivek Yukti Sharma Ayush Deepak Ramola Gaurav Velusamy Sudha Rendering automatic bokeh recommendation engine for photos using deep learning algorithm Acta Universitatis Sapientiae: Informatica bokeh recommendation photography deep learning inceptionv3 vgg16 mobilenetv2 effects 68r15 |
| title | Rendering automatic bokeh recommendation engine for photos using deep learning algorithm |
| title_full | Rendering automatic bokeh recommendation engine for photos using deep learning algorithm |
| title_fullStr | Rendering automatic bokeh recommendation engine for photos using deep learning algorithm |
| title_full_unstemmed | Rendering automatic bokeh recommendation engine for photos using deep learning algorithm |
| title_short | Rendering automatic bokeh recommendation engine for photos using deep learning algorithm |
| title_sort | rendering automatic bokeh recommendation engine for photos using deep learning algorithm |
| topic | bokeh recommendation photography deep learning inceptionv3 vgg16 mobilenetv2 effects 68r15 |
| url | https://doi.org/10.2478/ausi-2022-0015 |
| work_keys_str_mv | AT kumarrakesh renderingautomaticbokehrecommendationengineforphotosusingdeeplearningalgorithm AT guptameenu renderingautomaticbokehrecommendationengineforphotosusingdeeplearningalgorithm AT jaismeen renderingautomaticbokehrecommendationengineforphotosusingdeeplearningalgorithm AT dhantashreya renderingautomaticbokehrecommendationengineforphotosusingdeeplearningalgorithm AT pathaknishantkumar renderingautomaticbokehrecommendationengineforphotosusingdeeplearningalgorithm AT vivekyukti renderingautomaticbokehrecommendationengineforphotosusingdeeplearningalgorithm AT sharmaayush renderingautomaticbokehrecommendationengineforphotosusingdeeplearningalgorithm AT deepak renderingautomaticbokehrecommendationengineforphotosusingdeeplearningalgorithm AT ramolagaurav renderingautomaticbokehrecommendationengineforphotosusingdeeplearningalgorithm AT velusamysudha renderingautomaticbokehrecommendationengineforphotosusingdeeplearningalgorithm |